Abstract: Pile driving formulas and stress wave matching methods are commonly used to estimate the load capacity of piles. This paper investigates the feasibility of using neural networks to do this work. Neural networks attempt to simulate the process by which the human brain learns to discern patterns in arrays of data. The data used in this study were derived from actual pile driving records. The new method has been approved much more accurate and convinient than the traditional ones, as well as quite useful in research and in practice.